# Invock

> Invock — saiaathish-invock. Use this tool when you need to securely authorize and govern AI agent actions, ensuring compliance with policies and intent. Invock solves the problem of untrusted tool executions by validating data lineage and containment before allowing action, providing a secure and auditable execution environment. It integrates with existing systems, taking in policy and intent inputs and outputting authorized or denied tool calls.

Canonical page: https://skillsregistry.net/skills/saiaathish-invock  
JSON: https://api.skillsregistry.net/v1/skills/saiaathish-invock

## Description

Invock is a deterministic execution-trust layer for AI agents that authorizes tool calls against policy, intent, data lineage, and containment before execution. It integrates with MCP to provide secure, auditable action gating.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gkpi8ph66y)
- **Repository:** <https://github.com/saiaathish/Invock>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "saiaathish-invock"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/saiaathish-invock` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/saiaathish-invock/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt